internal-link-optimizer

Pass

Audited by Gen Agent Trust Hub on Apr 25, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill invokes a local Python helper script scripts/sitemap_urls.py to extract URL lists from website sitemaps.
  • [EXTERNAL_DOWNLOADS]: The Python script performs network requests to download XML sitemap content from user-provided or target URLs.
  • [DATA_EXFILTRATION]: The skill initiates outbound network connections via the urllib.request module in scripts/sitemap_urls.py to retrieve data from external web servers.
  • [PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection by ingesting and processing untrusted content from external sitemaps. Ingestion points: External XML data fetched and parsed by scripts/sitemap_urls.py. Boundary markers: Absent; there are no instructions or delimiters to prevent the agent from interpreting content within sitemap tags as commands. Capability inventory: The skill utilizes Read and Write tools and the ability to execute subprocesses (Python script) with network access. Sanitization: The script uses structured XML parsing to target <loc> tags, which provides basic filtering but does not validate or sanitize the string content of the URLs themselves.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 25, 2026, 12:13 AM